# Rethinking High-speed Image Reconstruction Framework with Spike Camera

arXiv: https://arxiv.org/abs/2501.04477 · HTML: https://mlsanity.com/paper/2501.04477/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 30 references that are in the map.
- First posted on arXiv 8 Jan 2025.

## Builds on (most cited first, 10 of 10)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Iterative Prompt Learning for Unsupervised Backlit Image Enhancement](https://mlsanity.com/paper/2303.17569/) (2023)
- [A Retina-inspired Sampling Method for Visual Texture Reconstruction](https://mlsanity.com/paper/1907.08769/) (2019)
- [Transfer CLIP for Generalizable Image Denoising](https://mlsanity.com/paper/2403.15132/) (2024)
- [Label-Free Event-based Object Recognition via Joint Learning with Image Reconstruction from Events](https://mlsanity.com/paper/2308.09383/) (2023)
- [E-CIR: Event-Enhanced Continuous Intensity Recovery](https://mlsanity.com/paper/2203.01935/) (2022)
- [SpikeCV: Open a Continuous Computer Vision Era](https://mlsanity.com/paper/2303.11684/) (2023)
- [Recurrent Spike-based Image Restoration under General Illumination](https://mlsanity.com/paper/2308.03018/) (2023)

## Built on by (most cited first, 1 of 1)

- [SPKLIP: Aligning Spike Video Streams with Natural Language](https://mlsanity.com/paper/2505.12656/) (2025)

## Abstract (arXiv)

Spike cameras, as innovative neuromorphic devices, generate continuous spike streams to capture high-speed scenes with lower bandwidth and higher dynamic range than traditional RGB cameras. However, reconstructing high-quality images from the spike input under low-light conditions remains challenging. Conventional learning-based methods often rely on the synthetic dataset as the supervision for training. Still, these approaches falter when dealing with noisy spikes fired under the low-light environment, leading to further performance degradation in the real-world dataset. This phenomenon is primarily due to inadequate noise modelling and the domain gap between synthetic and real datasets, resulting in recovered images with unclear textures, excessive noise, and diminished brightness. To address these challenges, we introduce a novel spike-to-image reconstruction framework SpikeCLIP that goes beyond traditional training paradigms. Leveraging the CLIP model's powerful capability to align text and images, we incorporate the textual description of the captured scene and unpaired high-quality datasets as the supervision. Our experiments on real-world low-light datasets U-CALTECH and U-CIFAR demonstrate that SpikeCLIP significantly enhances texture details and the luminance balance of recovered images. Furthermore, the reconstructed images are well-aligned with the broader visual features needed for downstream tasks, ensuring more robust and versatile performance in challenging environments.